Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add Aperivue/medsci-skills --skill verify-refsgit clone --depth 1 https://github.com/Aperivue/medsci-skillsWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/aperivue/medsci-skills/verify-refs)<a href="https://agentmods.dev/skills/aperivue/medsci-skills/verify-refs"><img src="https://agentmods.dev/badge/skills/aperivue/medsci-skills/verify-refs/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/aperivue/medsci-skills/verify-refs"><img src="https://agentmods.dev/badge/skills/aperivue/medsci-skills/verify-refs.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00060 | $0.03125 |
| Opus 5.5 | $0.00024 | $0.01250 |
| Sonnet 5.5 | $0.00012 | $0.00625 |
| Haiku 4.5 | $0.00006 | $0.00313 |
Grade A, and why
verify-refs scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 24d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 207 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Verify References (Audit-Only)
Audit an existing manuscript or bibliography for fabricated or mismatched references. This
skill never writes to references/ or manuscript/_src/refs.bib: corrections flow through
/lit-sync (Zotero → Better BibTeX → refs.bib), and /manage-project's
scripts/validate_project_contract.py flags any references/* file written here as drift. It
does not discover literature (/search-lit), and it never replaces a missing or bad citation
with a plausible alternative — replacements go through /search-lit or the user.
Inputs
- Manuscript or bibliography:
.md,.docx,.bib,.txt, or.tsv. - Optional project root. Default: current working directory.
- Optional flags:
--offline(extract and classify without API calls),--timeout N(HTTP timeout seconds),--strict,--no-openalex.
For markdown manuscripts with pandoc [@bibkey] citations, run a citation-key check first
(/manage-refs's check_citation_keys.py, or your reference manager's). It catches mis-keyed
cites; verify_refs.py catches fabricated metadata.
Deterministic Script
Run the bundled script rather than verifying citations by memory:
python "${CLAUDE_SKILL_DIR}/scripts/verify_refs.py" manuscript/manuscript.md --project-root .
For hooks or quick manual runs, use the wrapper:
"${CLAUDE_SKILL_DIR}/scripts/verify_cli.sh" manuscript/manuscript.md --offline
Manual pre-submission strict run:
"${CLAUDE_SKILL_DIR}/scripts/verify_cli.sh" manuscript/index.qmd --strict
--strict forbids --offline and exits non-zero on any UNVERIFIED row. Read
references/manual_checkpoint_guide.md for when to run it and what to do per status.
Lookups run PubMed (PMID) → CrossRef (DOI; doi.org's handle registry when CrossRef answers
404) → OpenAlex, with a PubMed title search last. Every
OK row rests on DOI, PMID, CrossRef, or PubMed title evidence; a failed lookup is recorded as
UNVERIFIED, never silently passed. A title search, in either index, counts only when a returned
title matches the cited one (the same token-similarity guard), so a made-up title cannot earn OK
from a search that merely returned something.
What ships with it
32 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- references/claim_evidence_workflow.md 6.7 KB
- references/manual_checkpoint_guide.md 3.3 KB
- scripts/_claim_evidence.py 16 KB runs code
- scripts/_quote_match.py 7.7 KB runs code
- scripts/check_claim_fidelity.py 33 KB runs code
- scripts/claim_fidelity_challenge/fixture/fulltext/10.1000_synthetic.oversight.md 3.4 KB
- scripts/claim_fidelity_challenge/fixture/fulltext/10.1000_synthetic.stub.md 910 B
- scripts/claim_fidelity_challenge/fixture/manuscript_numbered.md 769 B
- scripts/claim_fidelity_challenge/fixture/manuscript_shortsource.md 506 B
- scripts/claim_fidelity_challenge/fixture/manuscript_supported.md 732 B
- scripts/claim_fidelity_challenge/fixture/manuscript_unsupported.md 692 B
- scripts/claim_fidelity_challenge/fixture/refs.bib 588 B
- scripts/claim_fidelity_challenge/verify.sh 8.6 KB runs code
- scripts/verify_cli.sh 1.9 KB runs code
- scripts/verify_refs.py 72 KB runs code
- skill.yml 3.3 KB
- tests/fixtures/corporate_author.bib 821 B
- tests/fixtures/pagination_placeholder.bib 410 B
- tests/test_audit_source_path.sh 4.3 KB runs code
- tests/test_author_normalization.sh 3.9 KB runs code
- tests/test_bib_entry_headers.sh 6.5 KB runs code
- tests/test_bib_last_field.sh 4.6 KB runs code
- tests/test_bibtex_et_al.sh 4.6 KB runs code
- tests/test_claim_evidence.py 19 KB runs code
- tests/test_corporate_author.sh 2.2 KB runs code
- tests/test_doi_not_registered.sh 11 KB runs code
- tests/test_fabricated_author.sh 4.3 KB runs code
- tests/test_identifier_title.sh 12 KB runs code
- tests/test_markdown_reference_heading.sh 3.7 KB runs code
- tests/test_openalex_tier.sh 7.8 KB runs code
- tests/test_pagination_placeholder.sh 2.6 KB runs code
- tests/test_title_fallback_guard.sh 10 KB runs code
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 24d ago Changed · +8 lines 282664d1cfed
- 26d ago Changed · -57 lines · +18 tokens per session 9e1ace3bc468
- 27d ago Changed 1978537acdde
- 1mo ago Changed · +23 lines 09d8f8899feb
- 1mo ago First seen · 233 lines · 42 tokens per session scan A 95d6608cf159
verify-refs is a skill published in the GitHub repository Aperivue/medsci-skills (352 stars, last pushed today), licensed MIT. It adds 60 tokens to every session and 3,125 once invoked, about $0.0002 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
clinical-trials-search
Search ClinicalTrials.gov with natural language queries. Find clinical trials, enrollment, and outcomes using Valyu semantic search.
shidi
A Chinese-language research assistant role that turns a user’s ideas into literature reviews, experiment plans, figures and organised data.
clinical-research
Use when designing a prospective clinical study before submission — selecting and classifying endpoints (primary / key-secondary / exploratory, with surrogate-endpoint flagging), estimating sample size and power for two-arm designs (means / proportions / survival), or scoring a study plan for feasibility and a GO /…
sr-search-record
An automated literature-review search and screening workflow using OpenAlex, an open database and API for scholarly research, and Zotero, a reference manager.
critical-paper-reading
A paper-reading workflow for critically examining one research paper from a PDF or Zotero item. Zotero is a tool for organising research papers and references.
journal-requirements-check
A tool that extracts a journal's actual submission requirements and turns them into a traceable requirements matrix. A requirements matrix records each rule, its scope, whether it is mandatory or suggested, and any gap.